Altruistic coordination for multi-robot cooperative pathfinding

When multiple robots perform tasks in a shared workspace, they might be confronted with the risk of blocking each other’s ways, which will lead to conflicts or interference among them. Planning collision-free paths for all the robots is a challenge for a multi-robot system, which is also known as the multi-robot cooperative pathfinding problem in which each robot has to navigate from its starting location to the destination while keeping avoiding stationary obstacles as well as the other robots. In this paper, we present a novel fully decentralized approach to this problem. Our approach allows robots to make real-time responses to dynamic environments and can resolve a set of benchmark deadlock situations subject to complex spatial constraints in a shared workspace by means of altruistic coordination. Specifically, when confronted with congested situations, each robot can employ waiting, moving-forwards, dodging, retreating and turning-head strategies to make local adjustments. Most importantly, each robot only needs to coordinate and communicate with the others that are located within its coordinated network in our approach, which can reduce communication overhead in fully decentralized multi-robot systems. In addition, experimental results also show that our proposed approach provides an efficient and competitive solution to this problem.     

基于焦虑概念和拍卖方法的多机器人协作搜集

针对目前应用于多机器人搜集任务的拍卖方法很少考虑机器人参与拍卖的时机是否适当这一问题,在拍卖方法中引入了心理学的焦虑概念,提出了基于焦虑/拍卖的多机器人协作搜集方法.通过对机器人焦虑程度的量化反映其对环境、队友及自身状况的评价,进而反映其对自己独立完成任务的不自信程度和对队友提出的拍卖邀请的主观接受程度.实验结果表明,与单纯的拍卖方法相比,该方法能提高多机器人协作搜集任务的执行效率.     

多机器人合作与协调研究进展

介绍了多机器人合作与协调的国内外发展现状,重点讨论了多机器人合作与协调的研究载体——未知环境下的多机器人动态追捕问题,并针对不同的典型应用算法,作了简单的说明和比较。系统地阐明了多机器人合作与协调研究的有关方面,例如对象定义、环境探索、学习与决策、冲突消解等。在此基础上,对多机器人合作与协调的研究方向进行了展望。     

An algorithm for multi-robot collision-free navigation based on shortest distance

This paper presents a new approach for multi-robot navigation in dynamic environments, called the shortest distance algorithm. This approach uses both the current position and orientation of other robots to compute the collision free trajectory. The algorithm suggested in this paper is based on the concept of reciprocal orientation that guarantees smooth trajectories and collision free paths. All the robots move either in a straight line or in a circular arc using the Bresenham algorithms. The current approach is tested on three simulation scenarios.     

基于交换树的多机器人任务协调与负荷平衡方法

针对多机器人任务分工与协调过程中,未能有效解决的带任务偏序关系的负荷平衡问题,提出一种基于交换树的多机器人任务协调与负荷平衡方法。首先,通过有向赋权图（约束图）对带偏序关系约束的多机器人任务分工问题进行描述;其次,根据有向赋权图提出了初始任务分工策略,通过改进Dijkstra算法解决多机器人之间任务协调问题;最后,提出负荷平衡策略,通过交换树竞拍的方法解决机器人之间任务负荷不平衡问题。仿真结果表明,与一般Dijkstra方法相比,执行完任务负荷平衡策略之后,工作效率明显提高了12%,机器人之间的任务负荷差也减少了30%,验证了该方法的有效性。     

Response threshold models and stochastic learning automata for self-coordination of heterogeneous multi-task distribution in multi-robot systems

This paper focuses on the general problem of coordinating multiple robots. More specifically, it addresses the self-selection of heterogeneous specialized tasks by autonomous robots. In this paper we focus on a specifically distributed or decentralized approach as we are particularly interested in a decentralized solution where the robots themselves autonomously and in an individual manner, are responsible for selecting a particular task so that all the existing tasks are optimally distributed and executed. In this regard, we have established an experimental scenario to solve the corresponding multi-task distribution problem and we propose a solution using two different approaches by applying Response Threshold Models as well as Learning Automata-based probabilistic algorithms. We have evaluated the robustness of the algorithms, perturbing the number of pending loads to simulate the robot’s error in estimating the real number of pending tasks and also the dynamic generation of loads through time. The paper ends with a critical discussion of experimental results.     

A topological reinforcement learning agent for navigation

This article proposes a reinforcement learning procedure for mobile robot navigation using a latent-like learning schema. Latent learning refers to learning that occurs in the absence of reinforcement signals and is not apparent until reinforcement is introduced. This concept considers that part of a task can be learned before the agent receives any indication of how to perform such a task. In the proposed topological reinforcement learning agent (TRLA), a topological map is used to perform the latent learning. The propagation of the reinforcement signal throughout the topological neighborhoods of the map permits the estimation of a value function which takes in average less trials and with less updatings per trial than six of the main temporal difference reinforcement learning algorithms: Q-learning, SARSA, Q(λ)-learning, SARSA(λ), Dyna-Q and fast Q(λ)-learning. The RL agents were tested in four different environments designed to consider a growing level of complexity in accomplishing navigation tasks. The tests suggested that the TRLA chooses shorter trajectories (in the number of steps) and/or requires less value function updatings in each trial than the other six reinforcement learning (RL) algorithms.     

Cooperative multi-robot belief space planning for autonomous navigation in unknown environments

We investigate the problem of cooperative multi-robot planning in unknown environments, which is important in numerous applications in robotics. The research community has been actively developing belief space planning approaches that account for the different sources of uncertainty within planning, recently also considering uncertainty in the environment observed by planning time. We further advance the state of the art by reasoning about future observations of environments that are unknown at planning time. The key idea is to incorporate within the belief indirect multi-robot constraints that correspond to these future observations. Such a formulation facilitates a framework for active collaborative state estimation while operating in unknown environments. In particular, it can be used to identify best robot actions or trajectories among given candidates generated by existing motion planning approaches, or to refine nominal trajectories into locally optimal paths using direct trajectory optimization techniques. We demonstrate our approach in a multi-robot autonomous navigation scenario and consider its applicability for autonomous navigation in unknown obstacle-free and obstacle-populated environments. Results indicate that modeling future multi-robot interaction within the belief allows to determine robot actions (paths) that yield significantly improved estimation accuracy.     

Balancing task allocation in multi-robot systems using K-means clustering and auction based mechanisms

This paper aims to solve the balanced multi-robot task allocation problem. Multi-robot systems are becoming more and more significant in industrial, commercial and scientific applications. Effectively allocating tasks to multi-robots i.e. utilizing all robots in a cost effective manner becomes a tedious process. The current attempts made by the researchers concentrate only on minimizing the distance between the robots and the tasks, and not much importance is given to the balancing of work loads among robots. It is also found from the literature that the multi-robot system is analogous to Multiple Travelling Salesman Problem (MTSP). This paper attempts to develop mechanism to address the above two issues with objective of minimizing the distance travelled by ‘m’ robots and balancing the work load between ‘m’ robots equally. The proposed approach has two fold, first develops a mathematical model for balanced multi-robot task allocation problem, and secondly proposes a methodology to solve the model in three stages. Stage I groups the ‘N’ tasks into ‘n’ clusters of tasks using K-means clustering technique with the objective of minimizing the distance between the tasks, stage II calculates the travel cost of robot and clusters combination, stage III allocates the robot to the clusters in order to utilise all robot in a cost effective manner.     

基于风险策略的多单元连续双向拍卖的网格资源分配

针对计算网格资源的特点,提出一种基于风险策略的多单元连续双向拍卖的网格资源分配机制,实现对网格资源灵活有效的管理。首先,介绍了基于多单元连续双拍卖的网格资源分配框架。其次,针对计算网格资源的有限性,提出了RB2-MCDA机制。RB2-MCDA机制是在多单元连续双向拍卖中,代理采用Risk-Based2策略进行资源交易。Risk-Based2策略是一种基于风险行为的代理策略。实验结果表明,在不同规模的有限资源的计算网格中采用RB2-MCDA机制能够实现较高的资源分配效率,当资源需求量接近供给量时,分配效率超过99%。     

Stable navigation in formation for a multi-robot system based on a constrained virtual structure

This paper deals with the navigation in formation of a group of mobile robots. A set of virtual targets (points) forms a virtual structure of the same shape as the desired formation. Hence, to join and to remain in this formation, each robot has only to track one of these targets. In order to track the chosen target, it has to be attainable by the robot despite its kinematic constraints. This paper studies then the maximum allowed dynamic of the virtual structure according to the kinematic constraints of the robots. Both linear and angular velocities of the targets are constrained. Moreover, depending on these velocities, some relative positions (targets) in the formation become unattainable. These positions are also defined. A stable control law allows us to attain the generated set-points. Simulation and experimental results validate the proposed contributions.     

Vague拓扑空间和Vague连续映射*

基于Vague集现有理论、经典集合和Fuzzy集的拓扑理论,运用分析的方法推广了经典集合和Fuzzy集的相关拓扑理论,初步给出了Vague拓扑空间和Vague连续映射的概念,并就它们的一些性质进行了讨论。所得结果扩展了Vague集理论的研究范围,并提出了该领域未来可研究的方向。     

Spillover Algorithm: A decentralised coordination approach for multi-robot production planning in open shared factories

Open and shared manufacturing factories typically dispose of a limited number of industrial robots and/or other production resources that should be properly allocated to tasks in time for an effective and efficient system performance. In particular, we deal with the dynamic capacitated production planning problem with sequence independent setup costs where quantities of products to manufacture need to be determined at consecutive periods within a given time horizon and products can be anticipated or back-ordered related to the demand period. We consider a decentralised multi-agent variant of this problem in an open factory setting with multiple owners of robots as well as different owners of the items to be produced, both considered self-interested and individually rational. Existing solution approaches to the classic constrained lot-sizing problem are centralised exact methods that require sharing of global knowledge of all the participants’ private and sensitive information and are not applicable in the described multi-agent context. Therefore, we propose a computationally efficient decentralised approach based on the spillover effect that solves this NP-hard problem by distributing decisions in an intrinsically decentralised multi-agent system environment while protecting private and sensitive information. To the best of our knowledge, this is the first decentralised algorithm for the solution of the studied problem in intrinsically decentralised environments where production resources and/or products are owned by multiple stakeholders with possibly conflicting objectives. To show its efficiency, the performance of the Spillover Algorithm is benchmarked against state-of-the-art commercial solver CPLEX 12.8.     

Hierarchical multi-robot navigation and formation in unknown environments via deep reinforcement learning and distributed optimization

Compared with a single robot, Multi-robot Systems (MRSs) can undertake more challenging tasks in complex scenarios benefiting from the increased transportation capacity and fault tolerance. This paper presents a hierarchical framework for multi-robot navigation and formation in unknown environments with static and dynamic obstacles, where the robots compute and maintain the optimized formation while making progress to the target together. In the proposed framework, each single robot is capable of navigating to the global target in unknown environments based on its local perception, and only limited communication among robots is required to obtain the optimal formation. Accordingly, three modules are included in this framework. Firstly, we design a learning network based on Deep Deterministic Policy Gradient (DDPG) to address the global navigation task for single robot, which derives end-to-end policies that map the robot’s local perception into its velocity commands. To handle complex obstacle distributions (e.g. narrow/zigzag passage and local minimum) and stabilize the training process, strategies of Curriculum Learning (CL) and Reward Shaping (RS) are combined. Secondly, for an expected formation, its real-time configuration is optimized by a distributed optimization. This configuration considers surrounding obstacles and current formation status, and provides each robot with its formation target. Finally, a velocity adjustment method considering the robot kinematics is designed which adjusts the navigation velocity of each robot according to its formation target, making all the robots navigate to their targets while maintaining the expected formation. This framework allows for formation online reconfiguration and is scalable with the number of robots. Extensive simulations and 3-D evaluations verify that our method can navigate the MRS in unknown environments while maintaining the optimal formation.     

An enhanced topological map for efficient and reliable mobile robot navigation with imprecise sensors

An enhanced topological mapping system for efficient and reliable navigation is presented. The map has a topological framework and some additional features. Firstly, it utilizes such rough metrical information as the length and orientation of the links. Secondly, it provides a reliable localization algorithm with which the robot first finds the interval describing the robot’s probable location by estimating the projected traveled distance using dead reckoning and then fine-tunes the estimation using landmark detection modules. Finally, it provides a planning algorithm with which the robot’s path is chosen so that the robot reaches the goal location as fast as possible without losing its way despite using such imprecise sensors as ultrasonic range finders.We have implemented and tested the proposed mapping system both on a simulator and a real mobile robot, the CAIR-2. This paper also describes landmark detection modules that utilize ultrasonic range finders. Although landmark detection modules are too simple and imprecise to estimate position by themselves, these experiments show that the proposed mapping system can reliably guide robots.     

Approximate algorithms for static and continuous range queries in mobile navigation

For many years, spatial range search has been applied to computational geometry and multimedia problems to find interest objects within a given radius. Range search query has traditionally been used to return all objects within a given radius. However, having all objects is not necessary, especially when there are already enough objects closer to the query point. Furthermore, expanding the radius may give users better results, especially when there are a lot of objects just outside the search boundary. Therefore, in this paper, we focus on approximate range search, where the query results are approximate, rather than exact. We propose approximate static range search (ARS) which combines two approaches, namely (i) lowerbound approximate range search, and (ii) upperbound approximate range search. Using ARS, we are able to deliver a better performance, together with low false hit and reasonable false miss. We also extend ARS in the context of a continuous query setting, in which the query moves. This is particularly important in spatial databases as a mobile user who invokes the query is moving. In terms of continuous range search, the intention is to find split points—the locations where the query results will be updated. Accordingly, we propose two methods for approximate continuous range search, namely (i) range search minimization, and (ii) split points minimization. Our performance evaluation which compares our methods with the traditional continuous range search shows that our methods considerably reduce the number of split points, thereby improving overall performance.     

TopoPlan: a topological path planner for real time human navigation under floor and ceiling constraints

In this article we present TopoPlan, a topological planner dedicated to real-time humanoid path-planning and motion adaptation to floor and ceiling constraints inside complex static environments. This planner analyzes unstructured 3D triangular meshes in order to automatically determine their topology. The analysis is based on a prismatic spatial subdivision which is analyzed, taking into account humanoid characteristics, in order to extract navigable surfaces and precisely identify environmental constraints such as floors, ceilings, walls, steps and bottlenecks. The technique also provides a lightweight roadmap computation covering all accessible free space. We demonstrate the properties of our topological planner within the context of two reactive motion control processes: an on-the-fly trajectory optimization and foot print generation process that correctly handles climbing of complex staircases, and a reactive ceiling adaptation process that handles beam avoidance and motion adaptation to irregular floors and ceilings. We further show that the computation cost of these processes is compatible with the real time animation of several dozens of virtual humans.     

Fast and accurate map merging for multi-robot systems

We present a new algorithm for merging occupancy grid maps produced by multiple robots exploring the same environment. The algorithm produces a set of possible transformations needed to merge two maps, i.e translations and rotations. Each transformation is weighted, thus allowing to distinguish uncertain situations, and enabling to track multiple cases when ambiguities arise. Transformations are produced extracting some spectral information from the maps. The approach is deterministic, non-iterative, and fast. The algorithm has been tested on public available datasets, as well as on maps produced by two robots concurrently exploring both indoor and outdoor environments. Throughout the experimental validation stage the technique we propose consistently merged maps exhibiting very different characteristics.

Rehearsal versus map study as preparation for a flight navigation exercise

A flight simulator and a computer-generated depiction of an environment with both natural and cultural features were used to teach and test navigation knowledge. Conditions of guided rehearsal, unguided rehearsal, and map study were used to familiarize participants with the navigation environment. A subsequent route-following test of navigation knowledge in the simulated environment showed that unguided rehearsal was better than map study or guided rehearsal for the development of route knowledge. In addition, a pointing task revealed that unguided mission rehearsal was as good as map study for the development of survey knowledge. Actual or potential applications of this research include the use of simulator-based mission rehearsal for military flight operations.